Joint qualitative and quantitative evaluation of fast image dehazing based on dark channel prior

Lyes Aksas; Pierre-Jean Lapray; Alban Foulonneau; Laurent Bigué

doi:10.1117/12.2621566

20 May 2022 Joint qualitative and quantitative evaluation of fast image dehazing based on dark channel prior

Lyes Aksas, Pierre-Jean Lapray, Alban Foulonneau, Laurent Bigué

Author Affiliations +

Proceedings Volume 12136, Unconventional Optical Imaging III; 1213614 (2022) https://doi.org/10.1117/12.2621566
Event: SPIE Photonics Europe, 2022, Strasbourg, France

Conference Poster

Abstract

Haze is an undesirable effect in images caused when atmospheric particles, such as water droplets, ice crystals, dust, or smoke, are lit directly or indirectly by the sun. This effect can be counteracted by image processing, to bring back the details of a hazy image. Unfortunately, the execution time is often long, which prevents deployment in some video or real-time applications. In this paper, we propose to tune several parameters of the Dark Channel Prior method (DCP) algorithm combined with the fast guided filter. We evaluate the optimization in terms of execution time, and quantify the output image quality using different image quality metrics.

Citation Download Citation

Lyes Aksas, Pierre-Jean Lapray, Alban Foulonneau, and Laurent Bigué "Joint qualitative and quantitative evaluation of fast image dehazing based on dark channel prior", Proc. SPIE 12136, Unconventional Optical Imaging III, 1213614 (20 May 2022); https://doi.org/10.1117/12.2621566

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE